Use cases · Claude control plane

Your control planefor Claude.

Connect tools, secure every interaction, distribute access by team, and observe usage and spend. One platform to govern Claude across your organization.

Talk to us Read the Fermat story

Gateway · Policy line

Live

salesforce.update_opportunityallow ✓

slack.post_messageallow ✓

notion.searchallow ✓

crm.export_contactsblock · PII

hubspot.create_contactallow ✓

489

Sessions

4,412

Tool calls

Blocked

Trusted by Verizon

01 · The problem

Claude adoption is outpacing enterprise control

Without a control plane

How does it roll out?: Employees stand up Claude accounts one by one. No central place to approve tools, push updates, or give everyone the same vetted setup
Who sees the usage?: Once Claude is connected, no shared view of what actions run, who runs them, or what data moves through
What does it cost?: Token spend climbs across teams with no budgets or limits. Costs surface on the invoice, long after the usage that drove them

On the control plane

How does it roll out?: One vetted catalog of tools, provisioned team by team through your IdP
Who sees the usage?: Every session, tool call, and permission change in one searchable audit trail
What does it cost?: Budgets per team, enforced in real time, with every token attributed to a named employee

02 · The control plane

Build your control plane for Claude

Speakeasy sits between Claude and every system it touches. Connect tools, secure every interaction, distribute access by team, and observe usage and spend from one platform.

Every tool, one path to Claude

slack

github

linear

{}internal-api

gateway

Claude

1. Connect: Pre-built catalog: Salesforce, Slack, HubSpot; Internal APIs from an OpenAPI spec; Credentials vaulted, never exposed to the model

Works with every identity provider Okta

Any SAML / OIDC

03 · Proven at scale

From zero to company-wide in days

Fermat made Claude the operating system for their entire company using the Speakeasy AI control plane. These are the numbers.

Read the Fermat story

100%

Employee adoption

Every Fermat employee works through governed Claude access.

Days to rollout

From first connection to company-wide access.

+500%

MoM growth in AI usage

Usage grew after the rollout instead of being throttled by it.

Every agent

One control plane for every agent

Teams rarely settle on a single agent. The same rollout, oversight, and cost controls apply across Anthropic, OpenAI, Google, and the agents your teams build themselves.

AnthropicThis page

OpenAI Google Cursor

GitHub Copilot

OpenCode

Devin

Custom agents

Questions

What does a control plane for Claude do?

It sits between Claude and every system it touches, so the whole organization runs through one governed path. From a single platform you connect tools, secure every interaction, distribute access by team, and observe usage and spend. Claude usage scales without trading speed for safety.

How does Speakeasy connect Claude to enterprise systems?

Speakeasy provisions MCP servers for every tool and system Claude needs to reach. Pre-built connectors cover common SaaS like Salesforce, Slack, and HubSpot. Internal APIs become managed MCP servers from an OpenAPI spec. Everything goes through one governed path.

How does Claude authenticate to internal systems?

Through your existing identity provider. Speakeasy plugs into Okta, Microsoft Entra ID, Auth0, WorkOS, Google Workspace, or any SAML or OIDC provider. Claude inherits the user's existing roles and permissions, so no new account model is created and access stays consistent with what the user already has.

Can I scope which tools each team or person can access?

Yes. Provision sub-catalogs per team so engineering, sales, and finance each see only the MCP servers and toolsets relevant to their work. Permissions can scope down to the individual tool, and credential management replaces the pattern of users pasting API keys into Claude.

How is data exfiltration prevented?

Every prompt and response is inspected in real time. PII and exfiltration patterns are actively blocked. Prompt injection and shadow MCPs are passively detected. Alerts integrate with your existing SIEM, and a full audit trail records who asked what, when, against which data.

Does this work with Claude Enterprise specifically?

Yes. Speakeasy is designed to layer onto Claude Enterprise (and Claude Team) without changing the client. Users keep using Claude the way they already do; the control plane sits behind the scenes managing connections, identity, and policy.

What is the rollout pattern most companies follow?

Pick one team and one set of tools (often engineering with GitHub and Linear, or sales with Salesforce and Slack), route them through Speakeasy, prove value, then expand. Per-team registries make it easy to roll out to one team at a time without blocking the rest of the organization.

How does Speakeasy control Claude costs?

Token use is attributed to a team, user, and tool, so spend is never a black box. Set monthly budgets per team and enforce them in real time, with alerts as a team approaches its limit and a hard cap when it hits it. Leadership sees spend trending before the invoice arrives, and chargebacks hold up because every cost traces back to who incurred it.

AI everywhere.

Control here.

Talk to us Read the docs